Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Plane
    -0.07
    άνει
    -0.07
    遗
    -0.07
     health
    -0.06
     aluminium
    -0.06
     }).
    -0.06
    Print
    -0.06
    °C
    -0.06
    ALE
    -0.06
    相同
    -0.06
    POSITIVE LOGITS
     SUBSTITUTE
    0.07
     legion
    0.06
     Prahy
    0.06
    piel
    0.06
    /operator
    0.06
    .listBox
    0.06
    ocz
    0.06
     Corpus
    0.06
    assin
    0.06
    .Di
    0.06
    Act Density 0.215%

    No Known Activations